Search NASA⌕ Search

SEARCH · Search NASA

Results for “binary network”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 361 records · Page 20

Simultaneous prediction of structural properties in epitaxially–grown GaN with quantum and conventional multi–output learning algorithms

Hundreds of GaN thin film crystal plasma–assisted molecular beam epitaxy synthesis experiment records spanning two decades were organized into a dataset correlating the growth experiment design parameters with discrete, binary determinations of crystallinity and surface morphology. Conventional data science techniques as well as both quantum and classical multi–output supervised machine learning algorithms were implemented to investigate the relationships between the operating parameter data and the structural figures of merit. Correlation coefficients, decision tree nodes, p–values, and SHAP values all support substrate temperature and gallium effusion cell conditions as being statistically significant for simultaneously influencing GaN crystallinity and surface morphology. Here, a conventional deep neural network learned best from the data, followed by a quantum–classical hybrid gradient boosting algorithm. When combined with calculations of uncertainty intervals based on VennAbers predictors, machine learning predictions of both structural properties show good agreement with results reported in published experimental literature.

36 MATERIALS SCIENCE↗

Achieving Balanced Crystallization Kinetics of Donor and Acceptor by Sequential-Blade Coated Double Bulk Heterojunction Organic Solar Cells

Sequential deposition has great potential to achieve high performance in organic solar cells due to the resulting well-controlled vertical phase separation. In this work, double bulk heterojunction organic solar cells are fabricated by sequential-blade cast in ambient conditions. Probed by the in situ grazing incidence X-ray diffraction and in situ UV–vis absorption measurements, the seq-blade system exhibits a different tendency from each of the binary films during the film formation process. Due to the extensive aggregation of FOIC, the binary PBDB-T:FOIC film displays a strong and large phase separation, resulting in low current density (J sc) and unsatisfactory power conversion efficiency. In the seq-blade cast system, the bottom layer PBDB-T:IT-M produces many crystal nuclei for the top layer PBDB-T:FOIC, so the PBDB-T molecules are able to crystallize easily and quickly. Balanced crystallization kinetics between polymer and small molecule and an ideal percolation network in the film are observed. In addition, the balanced crystallization kinetics are favorable toward realizing lower recombination loss through charge transport processes.

14 SOLAR ENERGY↗

Hypereutectic Al-Ce-X (X=Mn, Cr, V, Mo, W) alloys fabricated by laser powder-bed fusion

Here, we characterize the microstructures and high-temperature mechanical properties of Al-2Ce and ternary Al-2Ce-1X (at.%) alloys fabricated by laser powder-bed fusion (LPBF), where X = Mn, Cr, V, Mo, and W are slow-diffusing transition metals. All ternary alloys show a hypereutectic microstructure in the as-LPBF state, containing an interconnected network of eutectic Al 11 Ce 3 phases (~10 vol.%) and an additional population of submicron, equiaxed Al 20 CeX 2 primary precipitates (~10 vol.%) which are isomorphous among these five alloys. Similar microstructures are present in arc-melted rods and atomized powders but are coarser due to the slower cooling rates in these processes. The hardness of the as-LPBF ternary Al-Ce-X alloys (1300–1400 MPa) is higher than that of the binary Al-Ce alloy (~1100 MPa) due to the higher volume fraction of strengthening phases. Furthermore, during exposure at 400 °C for up to three months, greater hardness retention is achieved in the ternary Al-Ce-X alloys (65–75%) than in the binary Al-Ce alloy (~55%), which is attributed to the extreme coarsening resistance of the Al 20 CeX 2 precipitates imparted by the very slow-diffusing ternary solute. These coarsening-resistant Al 20 CeX 2 precipitates also substantially improve alloy creep resistance, increasing the threshold stress for dislocation creep at 300°C from ~32 MPa for the binary Al-Ce alloy to ~77–100 MPa for the ternary Al-Ce-X alloys, and at 400°C from <10 MPa for the binary Al-Ce alloy to >40 MPa for the ternary Al-Ce-V alloy.

36 MATERIALS SCIENCE↗

Image processing pipeline for AI-driven nanoparticle megalibrary characterization

Recent innovations have made it possible to produce megalibraries, millions of structurally and compositionally distinct nanoparticles on a chip. These megalibraries yield vast volumes of data that are impossible to analyze manually, necessitating the development of automated tools. In previous work, we created a binary classification machine learning model to select quality nanoparticle images for downstream analysis. In this work, we show that adding a custom image processing step before training can produce significantly higher-performing models in a fraction of the time and make them more robust to different image noise levels and microscope acquisition settings. The image processing pipeline proposed here effectively cleans raw nanoparticle images, enhances key features, and allows us to use much lower resolution images and simpler neural network model architectures. These features result in higher performance and significant cost savings. Experiments demonstrate superior performance relative to baseline, including an 18.2% improvement in recall and a 13.1% increase in accuracy. Given the high cost of downstream analysis, it is critical to minimize false positives, and our best-performing model reaches a precision of 95.9% and a weighted F-score of 95.1% on an unseen test set. Additionally, model training time is reduced from hours to less than a minute. We also show that, using this custom image processing pipeline, model performance is significantly improved at lower pixel resolutions compared to downsizing alone. We expect that adopting this pipeline for AI-driven automated nanoparticle characterization will allow researchers to rapidly and accurately analyze much greater volumes of data, thereby accelerating materials discovery.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Decoding the protein–ligand interactions using parallel graph neural networks

Abstract Protein–ligand interactions (PLIs) are essential for biochemical functionality and their identification is crucial for estimating biophysical properties for rational therapeutic design. Currently, experimental characterization of these properties is the most accurate method, however, this is very time-consuming and labor-intensive. A number of computational methods have been developed in this context but most of the existing PLI prediction heavily depends on 2D protein sequence data. Here, we present a novel parallel graph neural network (GNN) to integrate knowledge representation and reasoning for PLI prediction to perform deep learning guided by expert knowledge and informed by 3D structural data. We develop two distinct GNN architectures: $$\hbox {GNN}_{\mathrm{F}}$$ GNN F is the base implementation that employs distinct featurization to enhance domain-awareness, while $$\hbox {GNN}_{\mathrm{P}}$$ GNN P is a novel implementation that can predict with no prior knowledge of the intermolecular interactions. The comprehensive evaluation demonstrated that GNN can successfully capture the binary interactions between ligand and protein’s 3D structure with 0.979 test accuracy for $$\hbox {GNN}_{\mathrm{F}}$$ GNN F and 0.958 for $$\hbox {GNN}_{\mathrm{P}}$$ GNN P for predicting activity of a protein–ligand complex. These models are further adapted for regression tasks to predict experimental binding affinities and $$\hbox {pIC}_{\mathrm{50}}$$ pIC 50 crucial for compound’s potency and efficacy. We achieve a Pearson correlation coefficient of 0.66 and 0.65 on experimental affinity and 0.50 and 0.51 on $$\hbox {pIC}_{\mathrm{50}}$$ pIC 50 with $$\hbox {GNN}_{\mathrm{F}}$$ GNN F and $$\hbox {GNN}_{\mathrm{P}}$$ GNN P , respectively, outperforming similar 2D sequence based models. Our method can serve as an interpretable and explainable artificial intelligence (AI) tool for predicted activity, potency, and biophysical properties of lead candidates. To this end, we show the utility of $$\hbox {GNN}_{\mathrm{P}}$$ GNN P on SARS-Cov-2 protein targets by screening a large compound library and comparing the prediction with the experimentally measured data.

59 BASIC BIOLOGICAL SCIENCES↗

X-RAY AND GAMMA-RAY FLASHES FROM TYPE Ia SUPERNOVAE?

We investigate two potential mechanisms that will produce X-ray and gamma-ray flashes from Type Ia supernovae (SN-Ia). The first mechanism is the breakout of the thermonuclear burning front as it reaches the surface of the white dwarf (WD). The second mechanism is the interaction of the rapidly expanding envelope with material within an accretion disk in the progenitor system. Our study is based on the delayed detonation scenario because this can account for the majority of light curves, spectra, and statistical properties of 'Branch-normal' SN-Ia. Based on detailed radiation-hydro calculations which include nuclear networks, we find that both mechanisms produce brief flashes of high-energy radiation with peak luminosities of 10{sup 48}-10{sup 50} erg s{sup -1}. The breakout from the WD surface produces flashes with a rapid exponential decay by 3-4 orders of magnitude on timescales of a few tenths of a second and with most of the radiation in the X-ray and soft gamma-ray range. The shocks produced in gases in and around the binary will produce flashes with a characteristic duration of a few seconds with most of the radiation coming out as X-rays and gamma-rays. In both mechanisms, we expect a fast rise and slow decline and, after the peak, an evolution from hard to softer radiation due to adiabatic expansion. In many cases, flashes from both mechanisms will be superposed. The X- and gamma-ray visibility of an SN-Ia will depend strongly on self-absorption within the progenitor system, specifically on the properties of the accretion disk and its orientation toward the observer. Such X-ray and gamma-ray flashes could be detected as triggered events by gamma-ray burst (GRB) detectors on satellites, with events in current GRB catalogs. We have searched through the GRB catalogs (for the BATSE, HETE, and Swift experiments) for GRBs that occur at the extrapolated time of explosion and in the correct direction for known Type Ia supernovae with radial velocity of less than 3000 km s{sup -1}. For the Burst and Transient Source Experiment (BATSE) about 12.9 +- 3.6 nearby SNe Ia should have been detected, but only 0.8 +- 0.7 non-coincidental matches have been found. With the High Energy Transient Explorer (HETE) and Swift satellites, we expect to see 5.6 +- 1.3 SN-Ia flashes from known nearby SNe Ia but, yet, no SN-Ia flashes were detected. With the trigger thresholds for these experiments and the upper limits on the SN-Ia distances, we show that the bolometric peak luminosity of SN-Ia flashes must be less approx10{sup 46} erg s{sup -1}. Our observational limit is several orders-of-magnitude smaller than the peak luminosities predicted for both the early flashes. We attribute this difference to the absorption of the X- and gamma-rays by the accretion disk of large-scale height or common envelope that would be smothering the WD.

79 ASTRONOMY AND ASTROPHYSICS↗

The Thermonuclear Runaway and the Classical Nova Outburst

Nova explosions occur on the white dwarf component of a cataclysmic variable binary stellar system that is accreting matter lost by its companion. When sufficient material has been accreted by the white dwarf, a thermonuclear runaway occurs and ejects material in what is observed as a classical nova explosion. Here, we describe both the recent advances in our understanding of the progress of the outburst and outline some of the puzzles that are still outstanding. We report on the effects of improving both the nuclear reaction rate library and including a modern nuclear reaction network in our one-dimensional, fully implicit, hydrodynamic computer code. In addition, there has been progress in observational studies of supernovae Ia with implications about the progenitors, and we discuss that in this review.

79 ASTRONOMY AND ASTROPHYSICS↗

Effects of the Cr{sub 2}O{sub 3} Content on the Viscosity of CaO-SiO{sub 2}-10 Pct Al{sub 2}O{sub 3}-Cr{sub 2}O{sub 3} Quaternary Slag

The present study experimentally investigates the effect of Cr{sub 2}O{sub 3} on the viscosity of molten slags. The viscosities of CaO-SiO{sub 2}-10 pct Al{sub 2}O{sub 3}-Cr{sub 2}O{sub 3} quaternary slags with two different binary basicities (R, basic slag with R = 1.2 and acidic slag with R = 0.8) were measured by the rotating cylindrical method from 1813 K to 1953 K (1540 °C to 1680 °C). The results showed that the viscosity of both types of slag decreased as the Cr{sub 2}O{sub 3} content increased, but the viscosity of acidic slags exhibited a greater decrease. The slags showed good Newtonian behavior at such high temperatures. Cr{sub 2}O{sub 3} could act as a network modifier to simplify the Si-O-Si tetrahedral structure, as verified by the Raman spectral analysis, which was consistent with the decreasing trend of viscosity. The activation energy of viscous flow decreased slightly with increasing Cr{sub 2}O{sub 3}, but increasing the basicity seemed to be more effective in decreasing the viscosity than adding Cr{sub 2}O{sub 3}.

36 MATERIALS SCIENCE↗

Selective Carbon Dioxide Adsorption by Two Robust Microporous Coordination Polymers

In the present work we report the design, synthesis, crystal structure determination, and adsorption properties of two new cadmium-based porous coordination polymers, [Cd(pda) 0.5 (spiro-4-py) 0.5 (HCOO)]•2H 2 O•DMF (compound 1, pda = p-phenylenediacetate, spiro- 4-py = (2,2’,7,7’-tetra(pyridin-4-yl)-9,9’-spirobi[fluorene], DMF = N,N’-dimethylformamide) and [Cd 2 (pda)(spiro-4-py)(CH 3 COO) 2 ]•DMA (compound 2, DMA = N,N’-dimethylacetamide) with similar structures. The coordination between cadmium and two organic linkers, pda and spiro-4-py, has yielded two-dimensional frameworks with rhombic openings. Stacking of these two-dimensional networks does not block the openings but rather results in permanent porosity with one-dimensional channels in the final structures. The permanent porosity of these compounds is confirmed by gas adsorption measurements. Compounds 1 and 2 have BET (Brunauer-Emmett-Teller) surface areas of 687 and 584 m 2 /g, respectively. Both compounds show favorable adsorption towards carbon dioxide over other light gases such as nitrogen, oxygen, and carbon monoxide. IAST (Ideal adsorbed solution theory) is employed to predict the adsorption selectivity of binary gas mixtures. Though compounds 1 and 2 possess similar structures, differences are observed in their gas adsorption behaviors, which can be attributed to their different terminal ligands of formate and acetate, respectively. Strikingly, both compounds show exceptionally high stability in aqueous media with a wide pH range, a characteristic that is highly desirable for gas separation-related applications. The robustness of these structures suggests that the use of hydrophobic spiro based multipyridine ligands can lead to water stable frameworks built on late-transition metals that are otherwise sensitive to moisture.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Correction to Selective Carbon Dioxide Adsorption by Two Robust Microporous Coordination Polymers

In the present work we report the design, synthesis, crystal structure determination, and adsorption properties of two new cadmium-based porous coordination polymers, [Cd(pda)0.5(spiro-4-py)0.5(HCOO)]•2H2O•DMF (compound 1, pda = p-phenylenediacetate, spiro- 4-py = (2,2’,7,7’-tetra(pyridin-4-yl)-9,9’-spirobi[fluorene], DMF = N,N’-dimethylformamide) and [Cd2(pda)(spiro-4-py)(CH3COO)2]•DMA (compound 2, DMA = N,N’-dimethylacetamide) with similar structures. The coordination between cadmium and two organic linkers, pda and spiro-4-py, has yielded two-dimensional frameworks with rhombic openings. Stacking of these two-dimensional networks does not block the openings but rather results in permanent porosity with one-dimensional channels in the final structures. The permanent porosity of these compounds is confirmed by gas adsorption measurements. Compounds 1 and 2 have BET (Brunauer-Emmett-Teller) surface areas of 687 and 584 m 2 /g, respectively. Both compounds show favorable adsorption towards carbon dioxide over other light gases such as nitrogen, oxygen, and carbon monoxide. IAST (Ideal adsorbed solution theory) is employed to predict the adsorption selectivity of binary gas mixtures. Though compounds 1 and 2 possess similar structures, differences are observed in their gas adsorption behaviors, which can be attributed to their different terminal ligands of formate and acetate, respectively. Strikingly, both compounds show exceptionally high stability in aqueous media with a wide pH range, a characteristic that is highly desirable for gas separation-related applications. The robustness of these structures suggests that the use of hydrophobic spiro based multipyridine ligands can lead to water stable frameworks built on late-transition metals that are otherwise sensitive to moisture.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Sap Velocity Data for Urban Trees in Chicago, Illinois (2024-2025)

This dataset contains uncorrected sap velocity measurements using the heat ratio method (HRM) collected using ICT International SFM1x sensors at five urban sites in Chicago, Illinois, as part of the DOE CROCUS project. The data includes continuous monitoring of sap velocity from various tree species, including Maples (Acer spp.): Sugar Maple (Acer saccharum), Silver Maple (Acer saccharinum), and Red Maple (Acer rubrum); Oaks (Quercus spp.): Swamp White Oak (Quercus bicolor); American Elm (Ulmus americana); Honey Locust (Gleditsia triacanthos); Cottonwood (Populus deltoides); and Tree of Heaven (Ailanthus altissima) across Chicago State University (CSU), Northeastern Illinois University (NEIU), Northwestern University (NU), University of Illinois Chicago (UIC), and West Woodlawn "Blacks in Green" (BIG). These include both street trees and those in urban park locations. Measurements were collected at 15-20 minute intervals, depending on the sensor, and transmitted via Long Range Wide Area Network (LoRaWAN) protocols. The wireless data was collected by Sage Network (https://sagecontinuum.org/) nodes. The dataset includes sensor ID, Global Positioning System (GPS) coordinates, tree species (common and scientific names), tree identification number, diameter at breast height (DBH in cm), uncorrected sap velocity measurements (cm/hr) from both inner and outer probes, and Sage Node identifiers so the data can be mapped to related variables such as air quality and wind speed that were collected on the Sage nodes. All timestamps are in local Chicago time (CDT/CST). Quality control flags are provided using a 3-bit binary system indicating physical range violations (< -10 or > 60 cm/hr), step spikes (absolute difference > 36 cm/hr), and stuck sensor conditions (> 10 consecutive identical values). These are raw data, not corrected for wood anatomy or species-specific characteristics. Data is provided in comma separated (CSV) format. This dataset is part of a larger collection of CROCUS environmental monitoring data, including linked datasets from Air Quality Transmitter (AQT) sensors, Weather Transmitter (WXT) sensors, and Multi-Function Research LoRaWAN (MFR) Nodes. DOIs for the supporting data are provided as part of this data package.

Chicago↗

Predictive analytics of selections of russet potatoes

We explore the application of machine learning algorithms specifically to enhance the selection process of Russet potato (Solanum tuberosum L.) clones in breeding trials by predicting their suitability for advancement. This study addresses the challenge of efficiently identifying high-yield, disease-resistant, and climate-resilient potato varieties that meet processing industry standards. Leveraging manually collected data from trials in the state of Oregon, we investigate the potential of a wide variety of state-of-the-art binary classification models. The dataset includes 1086 clones, with data on 38 attributes recorded for each clone, focusing on yield, size, appearance, and frying characteristics, with several control varieties planted consistently across four Oregon regions from 2013 to 2021. We conduct a comprehensive analysis of the dataset that includes preprocessing, feature engineering, and imputation to address missing values. We focus on several key metrics such as accuracy, F1-score, and Matthews correlation coefficient (MCC) for model evaluation. The top-performing models, namely a feedforward neural network classifier (Neural Net), a histogram-based gradient boosting classifier (HGBC), and a support vector machine classifier (SVM), demonstrate consistent and significant results. To further validate our findings, we conducted a simulation study using the aims, data-generating mechanisms, estimands, methods, and performance measures (ADEMP) framework, simulating different data-generating scenarios to assess model robustness and performance through true positive, true negative, false positive, and false negative distributions, area under the receiver operating characteristic curve (AUC-ROC) and MCC. The simulation results highlight that non-linear models like SVM and HGBC consistently show higher AUC-ROC and MCC than logistic regression, thus outperforming the traditional linear model across various distributions, and emphasizing the importance of model selection and tuning in agricultural trials. Variable selection further enhances model performance and identifies influential features in predicting trial outcomes. The findings emphasize the potential of machine learning in streamlining the selection process for potato varieties, offering benefits such as increased efficiency, substantial cost savings, and judicious resource utilization. Our study contributes insights into precision agriculture and showcases the relevance of advanced technologies for informed decision-making in breeding programs.

60 APPLIED LIFE SCIENCES↗

Molecular Dynamics Simulation of the Structure and Properties of CaO-SiO{sub 2}-CaF{sub 2} Slag Systems

As a fundamental slag system in metallurgical processes, the CaO-SiO{sub 2}-CaF{sub 2} system, its properties, and related microstructures are of critical importance. The effect of the binary basicity and addition of CaF{sub 2} on the structure and viscosity of CaO-SiO{sub 2}-CaF{sub 2} slag were investigated using molecular dynamics simulations and Fourier transform infrared spectrometry. The average bond lengths of Si-O, Ca-O, and O-O were 1.61, 2.31, and 2.61 Å, respectively, and the coordinate number of Si remained constant. O-Si-O maintained an angle of 109.2, which was considered to be unaffected by the basicity changes. With increasing basicity, the network connectivity degrees Q{sup 3} and Q{sup 4} decreased, and the microstructure of the melt was significantly simpler. The effect of CaF{sub 2} on the depolymerization of the network structure was not obvious, and CaF{sub 2} acted mainly as a diluent. The calculations showed that the viscosity decreased upon setting up a ratio of nonbridging oxygen over tetrahedrally coordinated atoms (NBO/T). A good linear relationship was confirmed between the viscosity of the molten slag and the NBO/T.

36 MATERIALS SCIENCE↗

Dynamics and Structure of Molten Neodymium Titanate

Binary rare earth titanates can be vitrified using levitation melt quenching, and their glasses are promising for optical applications. To better understand their thermophysical properties and dynamics, we have used molecular dynamics (MD) and empirical potential structure refinement (EPSR) to simulate molten neodymium titanate, 83TiO 2 –17Nd 2 O 3 . The models are compared with high-energy synchrotron X-ray diffraction of the melt structure over 1060–1960 K and thermophysical property measurements of electrostatically levitated droplets over 1500–2200 K. As temperature increases, the network periodicity increases and the correlation length decreases, both in monotonic trends that suggest continuous structural evolution through the melt and supercooled liquid regimes. At 1900 K, the mean Ti–O and Nd–O coordination numbers are 5.8(5) and 6.7(5), compared to the glass, 5.72(6) and 7.70(26). The equilibrium melting point is measured as 1860(20) K, over 100 K higher than previous estimates. Viscosity data from MD are in good agreement with experimental measurements. The dynamic propensity of Nd is similar to that of the network-forming Ti, suggesting that Nd does not participate as a conventional modifier. The viscosity of this fragile liquid is likely controlled by the breaking of cation–oxygen bonds and rearrangements of Ti–O polyhedra.

molecular dynamics↗

AGGREGATE: dAta-driven modelinG preservinG contRollable dEr for outaGe mAnagemenT and rEsiliency (Final Report)

The AGGREGATE project team successfully developed and validated various modules for outage management. Brief summaries of each module are provided to showcase their strength for outage management and restoration for a distribution system with a high penetration of connected distribution energy resources (DERs). In recent years, inverter-based DERs have been widely deployed in distribution system. A most of behind-the-meter (BTM) solar power generation is not visible to the utility. The data-driven DER and load estimation modules are using machine learning (ML) and artificial intelligence (AI) to manage this issue, which provides an opportunity for distribution system operators (DSOs) to operate systems and make decisions in real-time for a distribution system with a high penetration of DERs deployed. Also, the estimated DER and true load can be further leveraged in network aggregation and cold-load pick up estimation for reducing the computing complexity and providing for fast restoration. After load demand and DER power generations have been estimated, the information will support topology and state estimation (SE). The topology estimation module demonstrated the viability of mixed integer linear programming (MILP) formulation to estimate the most likely operational radial topology and outage sections using power flow measurements, historical/estimated load and DERs data and smart meter ping measurements. Formulation includes continuous (power flow, load and DERs data) and binary measurements (smart meter ping measurements) in a single formulation. Errors in continuous data and binary data are modeled as normal distribution and Bernoulli distribution, respectively. In the future distribution grid, the power injection from controllable DERs will be essential for efficient and resilient grid operation. However, determining the optimal DER injections and restoration actions is dependent on knowledge of the system states. State estimation (SE), already the cornerstone of transmission energy management systems, will become commonplace in distribution management systems as more measurements become available from deployment of automated metering infrastructure (AMI). Observability analysis is the first step in SE, as it determines the sufficiency of the available measurements for accurately estimating the current system states. A new type of pseudo-measurement called a Correlational Measurement (CM) is introduced in this module, to enhance the observability of the system to enable more accurate SE. CMs encapsulate knowledge of correlation between demand patterns for similar classes of loads as well as injection patterns for same-technology renewable DERs. During grid contingency scenarios, DERs have been traditionally disconnected, without any fault ride-through capabilities. However, with new regulations and better technology, it is feasible for these resources to contribute to the grid’s restoration after an adverse event and hence enhance resilience. The controllability module proposes a two-step restoration scheme for the power system restoration process by leveraging additional degrees of freedom in power electronics interfaced DERs for mitigating voltage problems. In a resilience mode without the utility system, the distribution grid relies on DERs to serve critical load. In such a severe event with multiple faults on the distribution feeders, actuation of various protective devices (PDs) divides the distribution system into electrical islands. The undetected actuated PDs due to fault current contributions from DERs can delay the restoration process, thereby reducing the system resilience. The Advanced Outage Management (AOM) and the Advanced Feeder Restoration (AFR) modules developed in this project provide improved system resilience with multiple DERs. AOM identifies the faulted sections and actuated PDs in a distribution system with DERs by incorporating smart meter data. The most credible outage scenario including fault locations, PD actuations, and fault indicator (FI) failures is identified by a set of binary integer linear programming incorporating hypotheses. The AFR module serves to restore a distribution system with available energy resources taking into consideration the availability of utility sources and DERs. By partitioning the system into islands, critical load will be served with the available generation resources within islands based on the solution of a MILP. When the utility systems become available, the optimal path will be determined by a spanning tree search algorithm that reconnects these islands back to substations and restores the remaining load. The transmission and distribution (T&D) co-simulation module was used to validate the effect of a control action performed on the distribution side assets as it propagates to the transmission side. This ensures that the control action performed results in a feasible operating point on both the transmission and the distribution system. In addition to validation, the team used the T&D co-simulation module to demonstrate how distribution system assets can be used to mitigate issues on the transmission system. Specifically, the team demonstrated that appropriate switching operations on the distribution side can alleviate the line overload condition on the transmission side without causing new operational constraint violations.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Using Machine Learning for Quantum Annealing Accuracy Prediction

Quantum annealers, such as the device built by D-Wave Systems, Inc., offer a way to compute solutions of NP-hard problems that can be expressed in Ising or quadratic unconstrained binary optimization (QUBO) form. Although such solutions are typically of very high quality, problem instances are usually not solved to optimality due to imperfections of the current generations quantum annealers. In this contribution, we aim to understand some of the factors contributing to the hardness of a problem instance, and to use machine learning models to predict the accuracy of the D-Wave 2000Q annealer for solving specific problems. We focus on the maximum clique problem, a classic NP-hard problem with important applications in network analysis, bioinformatics, and computational chemistry. By training a machine learning classification model on basic problem characteristics such as the number of edges in the graph, or annealing parameters, such as the D-Wave’s chain strength, we are able to rank certain features in the order of their contribution to the solution hardness, and present a simple decision tree which allows to predict whether a problem will be solvable to optimality with the D-Wave 2000Q. We extend these results by training a machine learning regression model that predicts the clique size found by D-Wave.

97 MATHEMATICS AND COMPUTING↗

Federated Machine Learning-Based Anomaly Detection System for Synchrophasor Network Using Heterogeneous Data Sets: Preprint

Synchrophasor technology is widely deployed in the energy management system to monitor the grid health at micro level and perform necessary corrective actions in real time; however, integrated phasor devices and data aggregators are exposed to several cybersecurity threats. This paper proposes a federated ML(FML)-based ADS to detect several data integrity attacks in the synchrophasor network. The proposed approach integrates the horizontal FML technique and consists of substation-based local models and a control center-based global model. The proposed methodology includes training local models using heterogeneous data sets that include network and grid information and updating the global model through multiple iterations by sharing model gradients. Finally, the trained global model is applied to identify cyberattacks, normal operation, and physical events. To validate the proof of concept, we used synthetic data sets generated by Mississippi State University and Oak Ridge National Laboratory for training and testing the classification models using the National Renewable Energy Laboratory's high performance computing resources. Our experimental results, computed through several performance measures, reveal that the proposed approach shows consistent performance during the binary, three-class, and multiclass classifications while ensuring privacy of synchrophasor data.

anomaly detection system↗